Saved in:
Bibliographic Details
Main Authors: Kraljevic, Zeljko, Yeung, Joshua Au, Bean, Daniel, Teo, James, Dobson, Richard J.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.10848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912156556984320
author Kraljevic, Zeljko
Yeung, Joshua Au
Bean, Daniel
Teo, James
Dobson, Richard J.
author_facet Kraljevic, Zeljko
Yeung, Joshua Au
Bean, Daniel
Teo, James
Dobson, Richard J.
contents Foresight 2 (FS2) is a large language model fine-tuned on hospital data for modelling patient timelines (GitHub 'removed for anon'). It can understand patients' clinical notes and predict SNOMED codes for a wide range of biomedical use cases, including diagnosis suggestions, risk forecasting, and procedure and medication recommendations. FS2 is trained on the free text portion of the MIMIC-III dataset, firstly through extracting biomedical concepts and then creating contextualised patient timelines, upon which the model is then fine-tuned. The results show significant improvement over the previous state-of-the-art for the next new biomedical concept prediction (P/R - 0.73/0.66 vs 0.52/0.32) and a similar improvement specifically for the next new disorder prediction (P/R - 0.69/0.62 vs 0.46/0.25). Finally, on the task of risk forecast, we compare our model to GPT-4-turbo (and a range of open-source biomedical LLMs) and show that FS2 performs significantly better on such tasks (P@5 - 0.90 vs 0.65). This highlights the need to incorporate hospital data into LLMs and shows that small models outperform much larger ones when fine-tuned on high-quality, specialised data.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10848
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models for Medical Forecasting -- Foresight 2
Kraljevic, Zeljko
Yeung, Joshua Au
Bean, Daniel
Teo, James
Dobson, Richard J.
Computation and Language
Artificial Intelligence
Machine Learning
Foresight 2 (FS2) is a large language model fine-tuned on hospital data for modelling patient timelines (GitHub 'removed for anon'). It can understand patients' clinical notes and predict SNOMED codes for a wide range of biomedical use cases, including diagnosis suggestions, risk forecasting, and procedure and medication recommendations. FS2 is trained on the free text portion of the MIMIC-III dataset, firstly through extracting biomedical concepts and then creating contextualised patient timelines, upon which the model is then fine-tuned. The results show significant improvement over the previous state-of-the-art for the next new biomedical concept prediction (P/R - 0.73/0.66 vs 0.52/0.32) and a similar improvement specifically for the next new disorder prediction (P/R - 0.69/0.62 vs 0.46/0.25). Finally, on the task of risk forecast, we compare our model to GPT-4-turbo (and a range of open-source biomedical LLMs) and show that FS2 performs significantly better on such tasks (P@5 - 0.90 vs 0.65). This highlights the need to incorporate hospital data into LLMs and shows that small models outperform much larger ones when fine-tuned on high-quality, specialised data.
title Large Language Models for Medical Forecasting -- Foresight 2
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.10848